A 1 km Global Carbon Flux Dataset Using In Situ Measurements and Deep Learning

Global carbon fluxes describe the carbon exchange between land and atmosphere. However, already available global carbon fluxes datasets have not been adjusted by the available site data and deep learning tools. In this work, a global carbon fluxes dataset (named as GCFD) of gross primary productivity (GPP), terrestrial ecosystem respiration (RECO), and net ecosystem exchange (NEE) has been developed via a deep learning based convolutional neural network (CNN) model. The dataset has a spatial resolution of 1 km at three time steps per month from January 1999 to June 2020. Flux measurements were used as a training target while remote sensing of vegetation conditions and meteorological data were used as predictors. The results showed that CNN could outperform other commonly used machine learning methods such as random forest (RF) and artificial neural network (ANN) by leading to satisfactory performance with R-2 values of the validation stage as 0.82, 0.72 and 0.62 for GPP, RECO, and NEE modelling, respectively. Thus, CNN trained using reanalysis meteorological data and remote sensing data was chosen to produce the global dataset. GCFD showed higher accuracy and more spatial details than some other global carbon flux datasets with reasonable spatial pattern and temporal variation. GCFD is also in accordance with vegetation conditions detected by remote sensing. Owing to the obtained results, GCFD can be a useful reference for various meteorological and ecological analyses and modelling, especially when high resolution carbon flux maps are required.

Automated summary

A global carbon fluxes dataset (GCFD) has been developed using a deep learning convolutional neural network (CNN) model. The dataset includes gross primary productivity (GPP), terrestrial ecosystem respiration (RECO), and net ecosystem exchange (NEE) at a spatial resolution of 1 km and three time steps per month from January 1999 to June 2020. The CNN model outperformed other machine learning methods and showed higher accuracy and more spatial details compared to other global carbon flux datasets. GCFD can be a valuable reference for meteorological and ecological analyses and modeling.